Llama 4 Maverick API Pricing — $0.20/M input, $0.60/M output
Meta's new frontier MoE model: stronger reasoning and coding than Scout with native multimodal vision, served on Groq LPUs.
Deprecated — use Muse Spark 1.1 (Meta)
No announced shutdown date. Source · Full retirement tracker
Speed
Not yet measured — see the speed benchmark leaderboard for models we do track.
Cost at scale
| Tokens / month | Est. cost (blended 3:1) |
|---|---|
| 100,000 | $0.03 |
| 1,000,000 | $0.30 |
| 10,000,000 | $3.00 |
| 100,000,000 | $30.00 |
How Llama 4 Maverick compares
Llama 3.1 8B — $0.06/MGPT-OSS 20B — $0.13/MGPT-OSS 120B — $0.26/MLlama 3.3 70B — $0.64/MQwen 3.8 30B — $1.20/MGPT-4o Mini — $0.26/MGrok-3 Mini — $0.26/MGPT-OSS 120B — $0.26/M
FAQ
Is Llama 4 Maverick cheaper than GPT-4o Mini?
Llama 4 Maverick costs $0.30/M blended tokens, GPT-4o Mini costs $0.26/M — GPT-4o Mini is cheaper.
How much does 1 million tokens cost with Llama 4 Maverick?
At a 3:1 input:output ratio, 1 million blended tokens costs approximately $0.30. Pure input costs $0.20/M; pure output costs $0.60/M.
Who provides Llama 4 Maverick?
Llama 4 Maverick is served by Groq. Pricing was last verified on 2026-07-10 against https://groq.com/pricing.